Comparison of algorithms that detect drug side effects using electronic healthcare databases
The electronic healthcare databases are starting to become more readily available and are thought to have excellent potential for generating adverse drug reaction signals. The Health Improvement Network (THIN) database is an electronic healthcare database containing medical information on over 11 mi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Published: |
Springer
2013
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/3343/ |
| _version_ | 1848791005091856384 |
|---|---|
| author | Reps, Jenna M. Garibaldi, Jonathan M. Aickelin, Uwe Soria, Daniele Gibson, Jack E. Hubbard, Richard B. |
| author_facet | Reps, Jenna M. Garibaldi, Jonathan M. Aickelin, Uwe Soria, Daniele Gibson, Jack E. Hubbard, Richard B. |
| author_sort | Reps, Jenna M. |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | The electronic healthcare databases are starting to become more readily available and are thought to have excellent potential for generating adverse drug reaction signals. The Health Improvement Network (THIN) database is an electronic healthcare database containing medical information on over 11 million patients that has excellent potential for detecting ADRs. In this paper we apply four existing electronic healthcare database signal detecting algorithms (MUTARA, HUNT, Temporal Pattern Discovery and modified ROR) on the THIN database for a selection of drugs from six chosen drug families. This is the first comparison of ADR signalling algorithms that includes MUTARA and HUNT and enabled us to set a benchmark for the adverse drug reaction signalling ability of the THIN database. The drugs were selectively chosen to enable a comparison with previous work and for variety. It was found that no algorithm was generally superior and the algorithms’ natural thresholds act at variable stringencies. Furthermore, none of the algorithms perform well at detecting rare ADRs. |
| first_indexed | 2025-11-14T18:21:37Z |
| format | Article |
| id | nottingham-3343 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T18:21:37Z |
| publishDate | 2013 |
| publisher | Springer |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-33432020-05-04T20:18:30Z https://eprints.nottingham.ac.uk/3343/ Comparison of algorithms that detect drug side effects using electronic healthcare databases Reps, Jenna M. Garibaldi, Jonathan M. Aickelin, Uwe Soria, Daniele Gibson, Jack E. Hubbard, Richard B. The electronic healthcare databases are starting to become more readily available and are thought to have excellent potential for generating adverse drug reaction signals. The Health Improvement Network (THIN) database is an electronic healthcare database containing medical information on over 11 million patients that has excellent potential for detecting ADRs. In this paper we apply four existing electronic healthcare database signal detecting algorithms (MUTARA, HUNT, Temporal Pattern Discovery and modified ROR) on the THIN database for a selection of drugs from six chosen drug families. This is the first comparison of ADR signalling algorithms that includes MUTARA and HUNT and enabled us to set a benchmark for the adverse drug reaction signalling ability of the THIN database. The drugs were selectively chosen to enable a comparison with previous work and for variety. It was found that no algorithm was generally superior and the algorithms’ natural thresholds act at variable stringencies. Furthermore, none of the algorithms perform well at detecting rare ADRs. Springer 2013-12 Article PeerReviewed Reps, Jenna M., Garibaldi, Jonathan M., Aickelin, Uwe, Soria, Daniele, Gibson, Jack E. and Hubbard, Richard B. (2013) Comparison of algorithms that detect drug side effects using electronic healthcare databases. Soft Computing, 17 (12). pp. 2381-2397. ISSN 1432-7643 Biomedical Informatics Data Mining http://link.springer.com/article/10.1007/s00500-013-1097-4 doi:10.1007/s00500-013-1097-4 doi:10.1007/s00500-013-1097-4 |
| spellingShingle | Biomedical Informatics Data Mining Reps, Jenna M. Garibaldi, Jonathan M. Aickelin, Uwe Soria, Daniele Gibson, Jack E. Hubbard, Richard B. Comparison of algorithms that detect drug side effects using electronic healthcare databases |
| title | Comparison of algorithms that detect drug side effects using electronic healthcare databases |
| title_full | Comparison of algorithms that detect drug side effects using electronic healthcare databases |
| title_fullStr | Comparison of algorithms that detect drug side effects using electronic healthcare databases |
| title_full_unstemmed | Comparison of algorithms that detect drug side effects using electronic healthcare databases |
| title_short | Comparison of algorithms that detect drug side effects using electronic healthcare databases |
| title_sort | comparison of algorithms that detect drug side effects using electronic healthcare databases |
| topic | Biomedical Informatics Data Mining |
| url | https://eprints.nottingham.ac.uk/3343/ https://eprints.nottingham.ac.uk/3343/ https://eprints.nottingham.ac.uk/3343/ |